Gen AI Engineer

QTech•Boston, CT

1d•Onsite

About The Position

We are seeking an experienced Gen AI Engineer with strong hands-on expertise in Python, Google Cloud Platform (GCP), Vertex AI, and modern Generative AI frameworks. The ideal candidate will have experience designing, developing, and deploying AI-powered applications using ADK, LangChain, LangGraph, RAG architectures, vector databases, and cloud-native technologies. The successful candidate will work closely with cross-functional teams to build scalable AI solutions, optimize agent workflows, and deploy production-ready AI applications.

Requirements

Strong hands-on Python Development
Generative AI Development
ADK (Agent Development Kit)
LangChain
LangGraph
Vertex AI
Vertex AI Agent Builder
Google Cloud Platform (GCP)
REST APIs
Microservices
Retrieval-Augmented Generation (RAG)
Embeddings
Vector Databases
Kubernetes
Docker
CI/CD Tools
Infrastructure as Code (Terraform)
Observability Tools (Logging, Monitoring, Tracing)
AI Agent Development
Agent Lifecycle Management
Reasoning Engines
Tool Chaining
Prompt Engineering
Context Management
Agent Orchestration
Performance Tuning
Debugging
AWS (Preferred)
Microsoft Azure (Preferred)

Nice To Haves

Experience developing enterprise-scale Generative AI applications.
Hands-on experience with Vertex AI Agent Builder.
Strong understanding of AI agent architecture and orchestration.
Experience deploying cloud-native AI applications on Google Cloud Platform.
Familiarity with AWS and Microsoft Azure cloud platforms.
Experience building scalable AI microservices.

Responsibilities

Develop and deploy Generative AI applications using Python.
Design and implement AI agent solutions using ADK, LangChain, and LangGraph.
Build AI-powered applications using Vertex AI and the Google Cloud Platform (GCP) ecosystem.
Develop and integrate REST APIs and microservices.
Design and implement Retrieval-Augmented Generation (RAG) architectures.
Work with embeddings and vector databases for semantic search and AI retrieval.
Deploy and manage AI applications on Google Cloud Platform, AWS, or Azure (GCP preferred).
Containerize applications using Docker and deploy on Kubernetes.
Implement CI/CD pipelines for AI application deployment.
Utilize observability tools for logging, monitoring, and tracing.
Implement Infrastructure as Code (IaC) using Terraform.
Optimize AI application performance through debugging and performance tuning.
Develop AI agents using Vertex AI Agent Builder.
Design intelligent agent workflows including reasoning engines and tool chaining.
Implement prompt engineering, context management, and agent orchestration techniques.
Collaborate with engineering teams throughout the SDLC to deliver enterprise AI solutions.